[FEAT][Functional]

README.md

@@ -13,36 +13,6 @@ pip install vision-mamba
 
 # Usage
 ```python
-<<<<<<< HEAD
-
-import torch
-from vision_mamba.model import Vim
-
-# Create a random tensor
-x = torch.randn(1, 3, 224, 224)
-
-# Create an instance of the Vim model
-model = Vim(
-    dim=256,  # Dimension of the model
-    heads=8,  # Number of attention heads
-    dt_rank=32,  # Rank of the dynamic routing tensor
-    dim_inner=256,  # Inner dimension of the model
-    d_state=256,  # State dimension of the model
-    num_classes=1000,  # Number of output classes
-    image_size=224,  # Size of the input image
-    patch_size=16,  # Size of the image patch
-    channels=3,  # Number of input channels
-    dropout=0.1,  # Dropout rate
-    depth=12,  # Depth of the model
-)
-
-# Perform a forward pass through the model
-out = model(x)
-
-# Print the shape and output of the forward pass
-print(out.shape)
-print(out)
-=======
 import torch
 from vision_mamba import Vim
 
@@ -68,7 +38,6 @@ model = Vim(
 out = model(x)  # Output tensor from the model
 print(out.shape)  # Print the shape of the output tensor
 print(out)  # Print the output tensor
->>>>>>> 9d8b929 ([CLEANUP])
 
 
 
@@ -92,13 +61,7 @@ print(out)  # Print the output tensor
 MIT
 
 
-<<<<<<< HEAD
-# Todo
-- [ ] Fix the encoder block with the forward and backward convolutions
-- [ ] Make a training script for imagenet
-=======
 
 # Todo
-- [ ] Fix the Encoder block
-- [ ] Implement the front and backward convolution
->>>>>>> 9d8b929 ([CLEANUP])
+- [ ] Create training script for imagenet
+- [ ] Create a visual mamba for facial recognition

example.py

@@ -1,39 +1,13 @@
 import torch
-<<<<<<< HEAD
 from vision_mamba.model import Vim
 
-# Create a random tensor
-x = torch.randn(1, 3, 224, 224)
-=======
-from vision_mamba import Vim
-
 # Forward pass
-x = torch.randn(1, 3, 224, 224)  # Input tensor with shape (batch_size, channels, height, width)
->>>>>>> 9d8b929 ([CLEANUP])
+x = torch.randn(
+    1, 3, 224, 224
+)  # Input tensor with shape (batch_size, channels, height, width)
 
 # Create an instance of the Vim model
 model = Vim(
-<<<<<<< HEAD
-    dim=256,  # Dimension of the model
-    heads=8,  # Number of attention heads
-    dt_rank=32,  # Rank of the dynamic routing tensor
-    dim_inner=256,  # Inner dimension of the model
-    d_state=256,  # State dimension of the model
-    num_classes=1000,  # Number of output classes
-    image_size=224,  # Size of the input image
-    patch_size=16,  # Size of the image patch
-    channels=3,  # Number of input channels
-    dropout=0.1,  # Dropout rate
-    depth=12,  # Depth of the model
-)
-
-# Perform a forward pass through the model
-out = model(x)
-
-# Print the shape and output of the forward pass
-print(out.shape)
-print(out)
-=======
     dim=256,  # Dimension of the transformer model
     heads=8,  # Number of attention heads
     dt_rank=32,  # Rank of the dynamic routing matrix
@@ -51,4 +25,3 @@
 out = model(x)  # Output tensor from the model
 print(out.shape)  # Print the shape of the output tensor
 print(out)  # Print the output tensor
->>>>>>> 9d8b929 ([CLEANUP])